A new artificial intelligence weather forecasting model developed by Google DeepMind has demonstrated superior performance to traditional numerical weather prediction systems in global medium-range forecasts. The model, named GraphCast, uses machine learning to analyze decades of historical weather data and current atmospheric conditions to predict weather patterns up to 10 days in advance. In head-to-head comparisons with the European Centre for Medium-Range Weather Forecasts’ high-resolution forecast (HRES), GraphCast provided more accurate predictions for over 90% of 1,380 test variables, including critical measurements like temperature, wind speed, and atmospheric pressure. The AI system can generate a 10-day forecast in under a minute on a single Google TPU v4 machine, significantly faster than conventional methods that require hours of computation on supercomputers. Researchers emphasize that AI models like GraphCast are designed to complement rather than replace traditional physics-based systems, offering a powerful new tool for meteorologists. Read the full article at: https://technologyreview.com/2024/01/15/ai-weather-model-outperforms-traditional-systems